Data fusion of Raman spectra in MSPC for fault detection and diagnosis in pharmaceutical manufacturing

• Published in: Computers & chemical engineering 2024-05, Vol.184, p.108647, Article 108647
• Main Authors: Jul-Jørgensen, I., Facco, P., Gernaey, K.V., Barolo, M., Hundahl, C.A.
• Format: Article
• Language: English
• Subjects: Data fusion; Fault detection; Fault diagnosis; Multivariate statistical process control; Pharmaceutical manufacturing; Raman spectroscopy
• ISSN: 0098-1354; 1873-4375
• DOI: 10.1016/j.compchemeng.2024.108647

This study investigates the use of Raman spectroscopy fused with other types of data (e.g., pH, temperature and turbidity) for multivariate statistical process control of two pharmaceutical case studies: one simulated industrial-scale fed-batch process for the production of penicillin and one real lab-scale crystallization process. The monitoring schemes are built on local principal component analysis models and hyper-parameters are tuned with regards to highest accuracy in fault detection. Accuracies above 90% are obtained for all types of data and level of DF. Furthermore, for the first case study the model built solely on spectra achieves higher fault detection rates, when only considering faults that also result in off-specification quality. This is supported by the fact that the fault is not necessarily detected when it occurs, but rather when it starts to affect quality variables as measured by the spectra. •MSPC model based solely on spectra predicts faulty, off-specification batches well•Model built on spectra does not detect faults when they start to affect the quality.•Low-level data fusion and mid-level data fusion achieve similar accuracy•Fault diagnosis easier using contributions to SPE rather than Hotellings T2